Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add deciqAI/knowledge-skills --skill seven-questions-testgit clone --depth 1 https://github.com/deciqAI/knowledge-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/deciqai/knowledge-skills/seven-questions-test)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/seven-questions-test"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/seven-questions-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/seven-questions-test"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/seven-questions-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00202 | $0.05606 |
| Opus 5 | $0.00101 | $0.02803 |
| Sonnet 5 | $0.00040 | $0.01121 |
| Haiku 4.5 | $0.00020 | $0.00561 |
Grade A, and why
seven-questions-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Seven Questions Test
Overview
Most business failures are not bad luck — they are unexamined answers. In Zero to One (2014, ch. 13), Peter Thiel and Blake Masters argue that every business must answer seven questions: Engineering (breakthrough technology, not incremental improvement), Timing (why now), Monopoly (big share of a small market), People (the right team), Distribution (a way to deliver, not just create), Durability (defensible in 10–20 years), and Secret (a unique opportunity others don't see). Thiel's calibration is blunt: answer all seven and you can build a monopoly; answer five or six and it might work; fewer, and failure will arrive looking like bad luck — but it wasn't luck, it was skipped questions.
The test's power is not the list — anyone can recite seven words. The power is the gate: each question demands a written, evidence-backed answer scored 1–5, and a question you cannot answer in writing with evidence scores a 1, not a hopeful 3. Vibes do not pass the gate. The book's own natural experiment makes the case: cleantech companies of the ~2005–2012 bubble routinely skipped four or more questions and died (Solyndra's 2011 bankruptcy is the emblem); Tesla, starting from the same sector in the same years, answered all seven.
This is the capstone skill of the Zero to One set — it operationalizes the others. Compose with monopoly-vs-competition (Q3 in depth) · zero-to-one-secrets (Q7 in depth) · last-mover-advantage (Q6 in depth) · definite-optimism (Q2's worldview) · contrarian-question (the interview form of Q7) · bullseye-traction-channels (Q5 in depth) · checklist (why written gates beat memory).
When to Use
Use when: deciding whether to start, fund, join, or seriously pivot a business; a plan is compelling on one axis (usually the tech or the TAM slide) and vague on the rest; preparing or evaluating a pitch and you want the holes found before an investor finds them; a previous venture failed "because of bad luck" and you want to know which questions were actually skipped; running an AI startup idea through a structured gate before building; user says "seven questions," "Thiel test," "is this idea any good," "stress-test my startup."
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 177 lines · 202 tokens per session scan A 8db32b7377f8
seven-questions-test is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 11d ago), licensed MIT. It adds 202 tokens to every session and 5,606 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
edge-tts
Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
tianqi
A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.
cto-advisor
Records technical decisions that serve a business outcome: constraints, architecture options, build-or-buy tradeoffs, and a justified skill selection. Use when the CEO asks "which architecture fits", "should we build or buy", "which skill should this department use", or "review our technical plan".
compliance-check
Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…
plan-payroll
Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…